Loading...
Loading...
Found 1,144 Skills
Use when authoring or normalising a specialist skill, or preparing to ship a feature or release — defines the seven evidence categories every specialist skill must declare against and provides the canonical Release Evidence Bundle template. The contract spine that turns scattered validation skills into a coherent ship-readiness check.
Run a structured discovery session to build an Allium specification through conversation. Use when the user wants to create a new spec from scratch, elicit or gather requirements, capture domain behaviour, specify a feature or system, define what a system should do, or is describing functionality and needs help shaping it into a specification.
Defines Steedos object data models using YAML. Objects represent database tables with fields, permissions, list views, and behaviors. Use this skill to create and configure objects, define fields, set up relationships, configure feature flags, and establish naming conventions. Modern format uses separate .field.yml, .listview.yml, .permission.yml, .button.yml files in subfolders.
Build standalone custom pages using Amis low-code framework, independent of object records. Pages are defined as paired .page.yml (metadata) and .page.amis.json (UI schema) files in main/default/pages/. Covers page types (app, list, record), render_engine configuration, pageAssignments for desktop/mobile, and Amis schema with components like service, crud, chart, form, wizard, tabs. Includes examples for dashboards, reports, and custom forms.
Create analytics question files (.question.yml) in Steedos projects. Questions are report/chart definitions stored as YAML seed data files, based on the @steedos-labs/analytics package (Metabase engine). Covers file format, dataset_query structure (MBQL), display types, visualization_settings, result_metadata, and file naming conventions.
Pinia v3 Vue state management with defineStore, getters, actions. Use for Vue 3 stores, Nuxt SSR, Vuex migration, or encountering store composition, hydration, testing errors.
Initialize a Harness Engineering framework in the current project. Use when user says 'harness', 'init harness', 'initialize framework', 'setup harness engineering', '/harness', or wants to set up a Plan-Build-Verify development workflow with specialized agents (planner, generator, evaluator). Creates CLAUDE.md, agent definitions, command templates, hooks, and documentation structure for autonomous AI-driven development.
Expert product management guidance for day-to-day PM work. Use when creating roadmaps, prioritizing features, managing stakeholders, planning sprints, grooming backlogs, scoping features, planning releases, defining OKRs, managing technical debt, or coordinating go-to-market. Covers RICE, ICE, MoSCoW frameworks, cross-functional collaboration, and product metrics.
Defines and tracks UX success through metrics, measurement frameworks, and experimentation. Part of the Intent design strategy system. Connects design decisions to observable evidence — did the thing we built actually help? Guards against measurement becoming manipulation. Trigger when: defining success metrics, designing A/B tests, building measurement frameworks, analyzing funnels, reviewing metric dashboards, questioning whether the right things are being measured, or when someone says "how do we know if this worked," "what should we measure," "let's run a test," or "the numbers look good but something feels off." Also trigger for ethical measurement reviews and counter-metric definition.
This skill should be used when the user asks to "manage alerts", "create alert", "list alerts", "check alert status", "enable alert", "disable alert", "investigate firing alerts", "check which alerts are active", "find alerting rules", "set up an alert", "configure alerting", "mute an alert", "silence an alert", "see alert definitions", "check alert priority", or wants to manage Coralogix alert definitions using the cx CLI.
Use when the user asks to design multi-agent systems, create agent architectures, define agent communication patterns, or build autonomous agent workflows.
Use when writing, reviewing, or committing code to enforce Karpathy's 4 coding principles — surface assumptions before coding, keep it simple, make surgical changes, define verifiable goals. Triggers on "review my diff", "check complexity", "am I overcomplicating this", "karpathy check", "before I commit", or any code quality concern where the LLM might be overcoding.